Download PDF
Methods Inf Med 2010; 49(05): 443-447
DOI: 10.3414/ME09-02-0039
Special Topic – Original Articles
Schattauer GmbH

Imaging the Thoracic Distribution of Normal Breath Sounds

R. González-Camarena
1   Department of Health Sciences, Universidad Autónoma Metropolitana, Mexico City, Mexico
,
S. Charleston-Villalobos
2   Department of Electrical Engineering, Universidad Autónoma Metropolitana, Mexico City, Mexico
,
A. Angeles-Olguín
2   Department of Electrical Engineering, Universidad Autónoma Metropolitana, Mexico City, Mexico
,
T. Aljama-Corrales
2   Department of Electrical Engineering, Universidad Autónoma Metropolitana, Mexico City, Mexico
› Author Affiliations
Further Information

Publication History

received: 19 October 2009

accepted: 14 June 2009

Publication Date:
17 January 2018 (online)

    Permissions and Reprints

Summary

Objective: To assess the feasibility to generate a confident image of normal breath sounds (BS) based on the quantitative analysis of multichannel sensors and imaging them in three known clinical classes, i.e., tracheal, bronchial and vesicular, identifying their spatial distribution with high resolution on the posterior thoracic surface.

Methods: Three parametrization techniques, the percentile frequencies, the univariate AR modeling, and the eigenvalues of the covariance matrix were evaluated when applied to BS. These sounds were acquired in twelve healthy subjects by a 5 × 5 sensor array on the posterior thoracic surface plus the sound at the tracheal position, to obtain feature vectors that fed a supervised multilayer neural network. Based on BS classification rate, the spatial distribution of each BS class was obtained by constructing an image using deterministic interpolation.

Results: The univariate AR modeling was the best parametrization technique producing a classification performance of 96% during the validation phase and just 4% of not classified feature vectors. Corresponding values for the percentile frequencies were 92% and 7.7%, whereas for the eigenvalues were 91% and 9.0%.

Conclusion: This work shows that it is possible to generate confident images associated with the distribution of normal BS classes. Therefore, a detailed image about the spatial distribution of BS in humans might be helpful for detecting lung diseases.

Keywords

Breath sounds - acoustic imaging - sound classification
 

  • References

  • 1 Vanderschoot J, Schreur HJ. AR (q, v) modeling of normal lung sounds. Methods Inf Med 1994; 33 (01) 24-27.
    Article in Thieme ConnectPubMedGoogle Scholar
  • 2 Gavriely N, Herzberg M. Parametric representation of normal breath sounds. J Appl Physiol 1992; 73 (05) 1776-1784.
    CrossrefPubMedGoogle Scholar
  • 3 Sovijärvi AR, Dalmasso F, Vanderschoot J, Malmberg LP, Righini G, Stoneman SA. Definition of terms for applications of respiratory sounds. Eur Respir Rev 2000; 10 (77) 597-610.
    PubMedGoogle Scholar
  • 4 Charleston-Villalobos S, González-Camarena R, Chi-Lem G, Aljama-Corrales T. Crackle sounds analysis by empirical mode decomposition. IEEE Eng Med Biol Mag 2007; 26 (01) 42-47.
    PubMedGoogle Scholar
  • 5 Laënnec RTH. De l’auscultation mediate ou traité du diagnostic de maladies des poumons et du coeur, fondé principalement sur ce nouveau moyen d’exploration. Paris: Brosson et Chaudé; 1819
    Google Scholar
  • 6 Pasterkamp H, Kraman S, Wodicka G. Respiratory sounds Advances beyond the stethoscope. Am J Respir Crit Care Med 1997; 156 (03) 974-987.
    CrossrefPubMedGoogle Scholar
  • 7 Charleston-Villalobos S, Cortés-Rubiano S, González-Camarena R, Chi-Lem G, Aljama-Corrales T. Respiratory acoustic thoracic imaging (RATHI): assessing deterministic interpolation techniques. Med Biol Eng Comput 2004; 42 (05) 618-626.
    CrossrefPubMedGoogle Scholar
  • 8 Dorantes-Mendez G, Charleston-Villalobos S, González-Camarena R, Chi-Lem G, AljamaCorrales T. Imaging of simulated crackle sounds distribution on the chest. In: Proc 30th Int Conf IEEE-EMBS; 2008 August 20-24; Vancouver, Canada: 2008. pp 4801-4804.
    Google Scholar
  • 9 Martinez-Hernandez G, Aljama-Corrales T, González-Camarena R, Charleston-Villalobos S, ChiLem G. Computerized classification of normal and abnormal lung sounds by multivariate linear autoregressive model. In: Proc 27th Ann Int Conf IEEE/EMBS; 2005 September 1-4; Shanghai, China: 2005. pp 1464-1467.
    Google Scholar
  • 10 Haykin S. Neural networks: a comprehensive foundation. 2nd edition. New Jersey: Prentice Hall; 1998
    Google Scholar
  • 11 Yosef M, Langer R, Lev S, Glickman YA. Effects of airflow rate on vibration response imaging in normal lungs. Open Respir Med J 2009; 3: 116-122.
    CrossrefPubMedGoogle Scholar
  • 12 Shykoff BE, Ploysongsang Y, Chang HK. Airflow and normal lung sounds. Am Rev Respir Dis 1988; 137 (04) 872-876.
    CrossrefPubMedGoogle Scholar
  • 13 Gavriely N, Cugell DW. Airflow effects on amplitude and spectral content of normal breath sounds. J Appl Physiol 1996; 80 (01) 5-13.
    CrossrefPubMedGoogle Scholar
  • 14 Ploysongsang Y, Iyer VK, Ramamoorthy PA. Reproducibility of the vesicular breath sounds in normal subjects. Respiration 1991; 58 3–4 158-162.
    CrossrefPubMedGoogle Scholar
  • 15 Mahagnah M, Gavriely N. Repeatability of measurements of normal lung sounds. Am J Respir Crit Care Med 1994; 149 2 Pt 1 477-481.
    CrossrefPubMedGoogle Scholar
  • 16 Sánchez I, Vizcaya C. Tracheal and lung sounds repeatability in normal adults. Respir Med 2003; 97 (12) 1257-60.
    CrossrefPubMedGoogle Scholar
  • 17 Kataoka H, Matsuno O. Age-Related Pulmonary Crackles (Rales) in Asymptomatic Cardiovascular Patients. Ann Fam Med 2008; 6: 239-245.
    CrossrefPubMedGoogle Scholar
  • 18 Workum P, Holford SK, Delbono EA, Murphy RLH. The prevalence and character of crackles (rales) in young women without significant lung disease. Am Rev Respir Dis 1982; 126 (05) 921-923.
    PubMedGoogle Scholar
  • 19 Thacker RE, Kraman SS. The prevalence of ausculatory crackles in subjects without lung disease. Chest 1982; 81 (06) 672-674.
    CrossrefPubMedGoogle Scholar